This record as markdown: /tools/cowork-os/open-application.md
What open_application does on CoWork OS
AI agents invoke open_application to trigger actions in CoWork OS. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why open_application is rated High
Opening an application triggers an external process on the host OS. An AI agent could misuse this to launch arbitrary applications (browsers, terminals, mail clients, etc.), potentially enabling further exploitation or unintended side effects.
From the tool's definition open_application — 'Open an application by name'
Attacks that exploit this kind of access
The rule that runs open_application safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CoWork OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For open_application, this is the rule to start with:
open_application stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every open_application call is checked against it from then on.
Questions about open_application
Open an application by name (e.g.,. It is categorised as a Execute tool in the CoWork OS MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CoWork OS MCP server in PolicyLayer and add a rule for open_application: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CoWork OS. Nothing to install.
open_application is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the open_application rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for open_application. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
open_application is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CoWork OS, and thousands of servers like it.
Across the catalogue